Adela Vagollari

Adela Vagollari

Auto-generated profile, based on publicly available information

Adela Vagollari

Institute for Digital Communications, Friedrich-Alexander-Universitt Erlangen-Nrnberg, Erlangen, Germany

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 June 2023 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
Ali BereyhiAli Bereyhi
Ali Bereyhi
AVAdela Vagollari
Adela Vagollari
SASaba Asaad
Saba Asaad
RMRalf R. Müller
Ralf R. Müller
WGWolfgang Gerstacker
Wolfgang Gerstacker
H. Vincent PoorH. Vincent Poor
H. Vincent Poor
This paper develops a class of low-complexity device scheduling algorithms for over-the-air federated learning via the method of matching pursuit. The proposed scheme tracks closely the close-to-optimal performance achieved by difference-of-convex programming, and outperforms significantly the well-known benchmark algorithms based on convex relaxation. Compared to the state-of-the-art, the proposed scheme imposes a drastically lower computational load on the system: for $K$ devices and $N$ antennas at the parameter server, the benchmark complexity scales with $(N^{2}+K)^{3} + N^{6}$ while the complexity of the proposed scheme scales with ${K^{p} N^{q}}$ for some $0 \lt p,q \leq 2$ . The efficiency of the proposed scheme is confirmed through the convergence analysis and numerical experiments on CIFAR-10 dataset.

26 May 2023 in IEEE Access
Verified
Journal Article
Open access
AVAdela Vagollari
Adela Vagollari
MHMartin Hirschbeck
Martin Hirschbeck
WGWolfgang Gerstacker
Wolfgang Gerstacker
Successful management of the radio spectrum requires, as a first step, detailed information about spectrum occupancy. In this work, we present an end-to-end deep learning (DL) based framework to obtain information from wide spectrum bands through signal detection, localization, and modulation classification. By visually representing the radio signals in spectrograms, we formulate the wideband detection problem as an object detection task from the computer vision field. To this end, the proposed framework consists of two cascaded modules: an object detection network repurposed to detect and classify distinctive signals in wideband spectrograms, and a convolutional neural network (CNN) designed to extend the classification capabilities to support a wide range of analog and digital modulation schemes. To evaluate our framework, we use a public wideband recognition dataset, which we carefully analyze and curate through a series of preprocessing techniques. To tackle the challenges of insufficient training data and class imbalance observed in the dataset, we suggest a training strategy that includes data mixing and transfer learning. Our experimental results on a general test set demonstrate that the proposed approach can detect and classify a variety of narrowband signals with simultaneously high precision (77.1%), recall (81.8%), and localization accuracy, as indicated by an average Intersection over Union (IoU) of 86%.

17 March 2025 in IEEE Access
Verified
Journal Article
Open access
AFAndreas Feder
Andreas Feder
AVAdela Vagollari
Adela Vagollari
RFRodrigo Fischer
Rodrigo Fischer
MHMartin Hirschbeck
Martin Hirschbeck
WGWolfgang Gerstacker
Wolfgang Gerstacker
The Paired Carrier Multiple Access (PCMA) technology is adopted in modern satellite communication systems. It establishes duplex links between two ground stations while enhancing the bandwidth efficiency by assigning two single-carrier (SC) signals to the same time-frequency resource. For a blind receiver for the satellite downlink signal in such system, in contrast to the cooperating transceivers of the duplex link, no information about signaling, training sequences or data is available. Yet, it requires accurate knowledge about the signal and channel parameters because the task of jointly demodulating and detecting the data of both included SC signals is rather challenging. In this paper, we present several statistics based estimators for the respective powers of the SC signals and the noise from the mixture signal. We illustrate the benefits of the respective power estimation approaches for different modulation schemes by providing a performance evaluation based on numerical simulations. To provide the estimators with the knowledge of the respective roll-off factors that are used by the transmitters to generate the SC signals, we introduce a neural network classifier for roll-off factor estimation.